Wasserstein distances are increasingly used in a wide variety of applications in machine learning. Sliced Wasserstein distances form an important subclass which may be estimated efficiently through one-dimensional sorting operations. In this paper, we propose a new variant of sliced Wasserstein distance, study the use of orthogonal coupling in Monte Carlo estimation of Wasserstein distances and draw connections with stratified sampling, and evaluate our approaches experimentally in a range of large-scale experiments in generative modelling and reinforcement learning.

A key stepping stone in the development of an artificial general intelligence (a machine that can perform any task), is the production of agents that can perform multiple tasks at once instead of just one. Unfortunately, canonical methods are very prone to catastrophic forgetting (CF) - the act of overwriting previous knowledge about a task when learning a new task. Recent efforts have developed techniques for overcoming CF in learning systems, but no attempt has been made to apply these new techniques to evolutionary systems. This research presents a novel technique, weight protection, for reducing CF in evolutionary systems by adapting a method from learning systems. It is used in conjunction with other evolutionary approaches for overcoming CF and is shown to be effective at alleviating CF when applied to a suite of reinforcement learning tasks. It is speculated that this work could indicate the potential for a wider application of existing learning-based approaches to evolutionary systems and that evolutionary techniques may be competitive with or better than learning systems when it comes to reducing CF.

Physical construction -- the ability to compose objects, subject to physical dynamics, in order to serve some function -- is fundamental to human intelligence. Here we introduce a suite of challenging physical construction tasks inspired by how children play with blocks, such as matching a target configuration, stacking and attaching blocks to connect objects together, and creating shelter-like structures over target objects. We then examine how a range of modern deep reinforcement learning agents fare on these challenges, and introduce several new approaches which provide superior performance. Our results show that agents which use structured representations (e.g., objects and scene graphs) and structured policies (e.g., object-centric actions) outperform those which use less structured representations, and generalize better beyond their training when asked to reason about larger scenes. Agents which use model-based planning via Monte-Carlo Tree Search also outperform strictly model-free agents in our most challenging construction problems. We conclude that approaches which combine structured representations and reasoning with powerful learning are a key path toward agents that possess rich intuitive physics, scene understanding, and planning.

Self-attention networks (SANs) have drawn increasing interest due to their high parallelization in computation and flexibility in modeling dependencies. SANs can be further enhanced with multi-head attention by allowing the model to attend to information from different representation subspaces. In this work, we propose novel convolutional self-attention networks, which offer SANs the abilities to 1) strengthen dependencies among neighboring elements, and 2) model the interaction between features extracted by multiple attention heads. Experimental results of machine translation on different language pairs and model settings show that our approach outperforms both the strong Transformer baseline and other existing models on enhancing the locality of SANs. Comparing with prior studies, the proposed model is parameter free in terms of introducing no more parameters.

Britain's leading position in developing self-driving cars could produce a £62bn economic boost by 2030, the car industry claimed – but warned that such potential could be jeopardised by a no-deal Brexit. A report published by the Society of Motor Manufacturers and Traders said the UK has significant advantages over other countries in pushing connected and autonomous vehicles, including forward-looking legislation allowing autonomous cars to be insured and driven on a greater proportion of roads than elsewhere. Mike Hawes, the chief executive of the SMMT, said more than £500m had been invested in research and development by industry and government, and another £740m in communications infrastructure to enable autonomous cars to work. He said: "The opportunities are dramatic – new jobs, economic growth and improvements across society. The UK's potential is clear. We are ahead of many rival nations but to realise these benefits we must move fast."

Her research has uncovered racial and gender bias in facial analysis tools sold by companies such as Amazon that have a hard time recognizing certain faces, especially darker-skinned women. Buolamwini holds a white mask she had to use so that software could detect her face. Facial recognition technology was already seeping into everyday life -- from your photos on Facebook to police scans of mugshots -- when Joy Buolamwini noticed a serious glitch: Some of the software couldn't detect dark-skinned faces like hers. That revelation sparked the Massachusetts Institute of Technology researcher to launch a project that's having an outsize influence on the debate over how artificial intelligence should be deployed in the real world. Her tests on software created by brand-name tech firms such as Amazon uncovered much higher error rates in classifying the gender of darker-skinned women than for lighter-skinned men.

NEW YORK - Danish toymaker Lego Group has unveiled a new robotics kit that encourages students to gain programming skills through collaborative, hands-on activities. Each set of the Spike Prime kit comes with over 500 pieces, for building a variety of creations, and is paired with lesson plans for both students and teachers. It also comes with an app that uses a drag-and-drop programming language. One of the models, called "Rain or Shine," is programmed to get data from a weather service, which then instructs a Lego robot to move its umbrella or sunglasses based on whether it is raining or sunny in a particular city. "Our intention is that every child in middle school should be able to have a very solid and valuable STEAM (Science, Technology, Engineering, Arts, Math) learning experience and ultimately to build that confidence," said Esben Staerk Joergensen, president of Lego Education.

Scientists have created an infrared body-scanner to help tackle surging violent crime rates. It combines a standard camera with infra-red technology to detect concealed blades from up to 20ft (6 metres) away and works through heavy clothing and even belts. The potentially life-saving technology's developers in the UK say it could one day be fitted to handheld cameras and even mobile phones. If it proves to be a viable option to law enforcement, it may be expanded to include other'geometrically similar' objects with a similar heat signature, such as stowed handguns. A proof of concept is expected in six months and if it is successful, has the potential to be implemented across the UK and around the world.

Artificial intelligence firm DeepMind has tackled games like Go and Starcraft, but now it is turning its attention to more sober affairs: how to solve school-level maths problems. Researchers at the company tasked an AI with teaching itself to solve arithmetic, algebra and probability problems, among others. It didn't do a very good job: when the neural network was tested on a maths exam taken by 16-year-olds in the UK, it got just 14 out of 40 questions correct, or the equivalent of an E grade.

Apple has cut the HomePod price by up to 18 percent in various regions as it seemingly tries to gain more of a foothold in a competitive market. As spotted by 9to5 Mac, the smart speaker is down from $349 to $299 in its US store, $449 to $399 in Canada and £319 to £279 in the UK. Third-party retailers have often offered discounts on HomePod, but it's the first official price drop from the mothership. The HomePod arrived only 14 months ago. The move could entice more people to buy a HomePod, though it's competing with many other recognizable brands at both its bracket and lower price points.